CN115205637A - Intelligent identification method for mine car materials - Google Patents
Intelligent identification method for mine car materials Download PDFInfo
- Publication number
- CN115205637A CN115205637A CN202211133562.4A CN202211133562A CN115205637A CN 115205637 A CN115205637 A CN 115205637A CN 202211133562 A CN202211133562 A CN 202211133562A CN 115205637 A CN115205637 A CN 115205637A
- Authority
- CN
- China
- Prior art keywords
- mine car
- preprocessed
- layer
- extraction module
- images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Abstract
The invention relates to the technical field of image recognition and processing, and provides an intelligent recognition method for mine car materials, which comprises the steps of collecting mine car material images, expanding and grouping the mine car material images, and constructing a training sample library; constructing a convolutional neural network model, and training the convolutional neural network model by using each group of samples in a training sample library; and 4 mine car material images to be identified are collected in a continuous time period, the 4 mine car material images to be identified are identified by using the trained convolutional neural network model, and an identification result is output. The method and the device can overcome environment diversity and improve accuracy.
Description
Technical Field
The invention relates to the technical field of mine car equipment, in particular to an intelligent identification method for mine car materials.
Background
At present, the gangue mixed in coal can reduce the combustion rate, and the combustion products can cause environmental pollution, so the gangue identification is an important link in the coal mine production and processing process, and is also an effective way for fully utilizing energy resources, reducing environmental pollution, saving human resources and improving production efficiency. At present, in a coal mine auxiliary shaft rail separate transportation system, mine cars need to be separately transported according to mine car material types, and mine car logistics are generally divided into three types of coal, gangue and sundries.
With the development of computer vision technology, especially the development of convolutional neural network, the mine car material identification method based on deep learning is gradually applied to the auxiliary shaft mine car track distribution system by the characteristics of low cost, convenient deployment and the like. However, the existing mine car material identification method has low accuracy, and the main reasons are as follows: (1) the number of training samples cannot meet the requirement; (2) Due to the diversity of environments, the performance of the algorithm cannot meet the generation requirement. Therefore, an intelligent identification method for mine car materials is needed to solve the problems.
Disclosure of Invention
In view of the above problems, the present application is provided to provide an intelligent mine car material identification method, which is used for overcoming environment diversity and improving accuracy.
The application provides an intelligent identification method for mine car materials, which comprises the following steps:
s1, acquiring mine car material images, expanding and grouping the mine car material images, and constructing a training sample library;
s2, constructing a convolutional neural network model, and training the convolutional neural network model by using each group of samples in a training sample library; each group of samples comprises 4 preprocessed material images, and the same mine car material images under different angles and noises are represented;
s3, collecting 4 mine car material images to be identified in a continuous time period, identifying the 4 mine car material images to be identified by using a trained convolutional neural network model, and outputting an identification result; the size of the continuous time period is set according to experience, and 4 mine car material images to be identified are ensured to represent coal, gangue or sundries at the same time.
Further, step S1 specifically includes:
s11, collecting mine car material images by using monitoring equipment arranged at the wellhead of the auxiliary shaft;
s12, respectively turning over each mine car material image to realize 2-time expansion to obtain a first pre-processing image, wherein the first pre-processing image comprises a turned mine car material image and a non-turned mine car material image;
s13, respectively rotating the first preprocessed image by using a random preset rotation angle to realize 6-time expansion to obtain a second preprocessed image, wherein the second preprocessed image comprises a left-turning first preprocessed image, a right-turning first preprocessed image and a non-rotating first preprocessed image;
and S14, respectively carrying out noise injection operation on the second preprocessed images to realize 24-time expansion to obtain preprocessed material images, wherein the preprocessed material images comprise the second preprocessed images injected by Gaussian noise, the second preprocessed images injected by multiplicative noise, the second preprocessed images injected by salt and pepper noise and the second preprocessed images injected without noise.
And S15, randomly dividing the 24 preprocessed material images after the expansion of each mine car material image into 6 groups of samples, wherein each group of samples comprises 4 preprocessed material images, and constructing a training sample library.
Further, the monitoring device is a camera.
Further, step S2 specifically includes:
step S21, constructing a first feature extraction module, a second feature extraction module, a third feature extraction module and a fourth feature extraction module;
step S22, constructing a splicing module for splicing the features output by the first feature extraction module, the second feature extraction module, the third feature extraction module and the fourth feature extraction module;
s23, sequentially constructing a full connection layer, a Dropout layer and a Softmax layer, and classifying the features output by the splicing module to generate a classification result;
and S24, training the convolutional neural network model by using each group of samples in the training sample library.
Further, the first feature extraction module, the second feature extraction module, the third feature extraction module and the fourth feature extraction module are identical in structure.
Furthermore, each feature extraction module comprises a first convolution layer, a first normalization layer, a second convolution layer, a second normalization layer, a third convolution layer, a first maximum pooling layer and a first average pooling layer;
inputting the preprocessed material image into a first convolution layer, wherein the convolution kernel size is 7 multiplied by 7, and the input end of the first normalization layer is connected with the output end of the first convolution layer; the input end of the second convolution layer is connected with the output end of the first normalization layer, the convolution kernel of the second convolution layer is 5 multiplied by 5, the input end of the second normalization layer is connected with the output end of the second convolution layer, the input end of the third convolution layer is connected with the output end of the second normalization layer, the convolution kernel of the third convolution layer is 3 multiplied by 3, the input end of the first maximum pooling layer is connected with the output end of the third convolution layer, and the input end of the first average pooling layer is connected with the output end of the first maximum pooling layer.
Further, the classification result is coal, gangue and sundries.
The beneficial effect of this application is:
(1) The application provides an intelligent identification method of mine car materials, which is used for carrying out expansion operation on collected mine car material images, identifying a convolutional neural network model by utilizing the same mine car material image under random different angles and noises, overcoming the environment diversity and improving the accuracy of convolutional neural network model identification.
(2) The method utilizes the convolutional neural network model to extract and identify the characteristics of 4 mine car material images of the same type in continuous time periods, comprehensively considers the environmental diversity and further improves the accuracy of mine car material image identification.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for intelligent identification of mine car materials provided herein;
FIG. 2 is a flow chart of the augmentation operation provided herein;
fig. 3 is a structural diagram of a convolutional neural network model provided in the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a plurality" typically includes at least two, but does not exclude the presence of at least one.
The application provides an intelligent identification method of mine car materials, which is used for carrying out expansion operation on collected mine car material images, and carrying out series on a convolutional neural network model by utilizing the same mine car material image under random different angles and noises, thereby overcoming the environment diversity and improving the accuracy of convolutional neural network model identification. Meanwhile, feature extraction and recognition are carried out on 4 mine car material images of the same type in a continuous time period by using a convolutional neural network model, environment diversity is comprehensively considered, and accuracy of mine car material image recognition is further improved.
The present application is further described with reference to the following figures and specific examples.
FIG. 1 is a flow chart of a method for intelligently identifying mine car materials according to an embodiment of the present application. As shown in FIG. 1, the intelligent identification method for mine car materials comprises the following steps:
s1, acquiring mine car material images, expanding and grouping the mine car material images, and constructing a training sample library.
In this embodiment of the present application, the step S1 specifically includes:
and S11, acquiring mine car material images by using monitoring equipment installed at the wellhead of the auxiliary shaft. Wherein the monitoring device may be a camera.
And S12, respectively turning over each mine car material image to realize 2-time expansion to obtain a first pre-processing image, wherein the first pre-processing image comprises a turned mine car material image and a non-turned mine car material image. A flow chart of a specific augmentation operation is shown in fig. 2.
And S13, respectively performing rotation operation on the first preprocessed image by utilizing a random preset rotation angle to realize 6-time expansion to obtain a second preprocessed image, wherein the second preprocessed image comprises a left-turning first preprocessed image, a right-turning first preprocessed image and a non-rotation first preprocessed image.
And S14, respectively carrying out noise injection operation on the second preprocessed images to realize 24-time expansion to obtain preprocessed material images, wherein the preprocessed material images comprise the second preprocessed images injected with Gaussian noise, the second preprocessed images injected with multiplicative noise, the second preprocessed images injected with salt and pepper noise and the second preprocessed images injected without noise.
And S15, randomly dividing the 24 preprocessed material images expanded by each mine car material image into 6 groups of samples, wherein each group of samples comprises 4 preprocessed material images, and constructing a training sample library.
The convolutional neural network algorithm has a plurality of parameters, a large number of training samples are needed for training the parameters to enable the parameters to work correctly, and due to the fact that the number of the coal images, the gangue images and the sundry images is small, the collected mine car material images are expanded, the original mine car material images are enlarged by 24 times, the problem that the convolutional neural network algorithm is over-fitted due to the fact that a training sample library is too small is solved, and accuracy of convolutional neural network algorithm identification is improved.
And S2, constructing a convolutional neural network model, and training the convolutional neural network model by using each group of samples in the training sample library.
In this embodiment of the present application, as shown in fig. 3, the step S2 specifically includes:
and S21, constructing a first feature extraction module, a second feature extraction module, a third feature extraction module and a fourth feature extraction module.
Specifically, the first feature extraction module, the second feature extraction module, the third feature extraction module and the fourth feature extraction module have the same structure.
Each feature extraction module comprises a first convolution layer, a first normalization layer, a second convolution layer, a second normalization layer, a third convolution layer, a first maximum pooling layer and a first average pooling layer.
The preprocessed material image is input into the first convolution layer, the convolution kernel size is 7 multiplied by 7, the input end of the first normalization layer is connected with the output end of the first convolution layer, and the convolution neural network is faster and more stable by arranging the normalization layer. The input end of the second convolution layer is connected with the output end of the first normalization layer, the convolution kernel size of the second convolution layer is 5 multiplied by 5, the input end of the second normalization layer is connected with the output end of the second convolution layer, the input end of the third convolution layer is connected with the output end of the second normalization layer, the convolution kernel size of the third convolution layer is 3 multiplied by 3, the input end of the first maximum pooling layer is connected with the output end of the third convolution layer, and the input end of the first average pooling layer is connected with the output end of the first maximum pooling layer.
According to the method and the device, pooling operation is omitted after the first convolution layer and the second convolution layer of the feature extraction module, and pooling operation is only adopted after the third convolution layer, so that loss of detail features caused by pooling operation can be prevented, the integrity of feature extraction is improved, and the accuracy of subsequent material image identification is improved.
Step S22, constructing a splicing module for splicing the features output by the first feature extraction module, the second feature extraction module, the third feature extraction module and the fourth feature extraction module;
and S23, sequentially constructing a full connection layer, a Dropout layer and a Softmax layer, and classifying the features output by the splicing module to generate a classification result. Wherein the classification result comprises coal, gangue and sundries.
And S24, training the convolutional neural network model by utilizing each group of samples in the training sample library.
In the application, 4 preprocessed material images are randomly selected from 24 preprocessed material images expanded by each mine car material image, and a convolutional neural network model is trained. Because the 4 preprocessed material images represent the same mine car material image under different angles and noises, the environment diversity can be overcome, the convolutional neural network model is comprehensively optimized, and the accuracy of convolutional neural network model identification is improved.
And S3, collecting 4 mine car material images to be identified in a continuous time period, identifying the 4 mine car material images to be identified by using the trained convolutional neural network model, and outputting an identification result. The size of the continuous time period is set according to experience, and 4 mine car material images to be recognized are ensured to represent coal, gangue or sundries at the same time.
In the application, the convolutional neural network model is utilized to perform feature extraction and identification on 4 continuous mine car material images of the same type, environment diversity is comprehensively considered, the learning capacity of the convolutional neural network model is improved, and the accuracy of mine car material image identification is further enhanced.
The foregoing description shows and describes several preferred embodiments of the present application, but as aforementioned, it is to be understood that the application is not limited to the forms disclosed herein, and is not to be construed as excluding other embodiments, but rather is capable of use in various other combinations, modifications, and environments and is capable of changes within the scope of the inventive concept as expressed herein, commensurate with the above teachings, or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the application, which is to be protected by the claims appended hereto.
Claims (7)
1. An intelligent identification method for mine car materials is characterized by comprising the following steps:
s1, acquiring mine car material images, expanding and grouping the mine car material images, and constructing a training sample library;
s2, constructing a convolutional neural network model, and training the convolutional neural network model by using each group of samples in a training sample library; each group of samples comprises 4 preprocessed material images, and the same mine car material images under different angles and noises are represented;
s3, collecting 4 mine car material images to be identified in a continuous time period, identifying the 4 mine car material images to be identified by using a trained convolutional neural network model, and outputting an identification result; the size of the continuous time period is set according to experience, and 4 mine car material images to be identified are ensured to represent coal, gangue or sundries at the same time.
2. The intelligent identification method according to claim 1, wherein step S1 specifically comprises:
s11, collecting mine car material images by using monitoring equipment arranged at the wellhead of the auxiliary shaft;
s12, respectively turning over each mine car material image to realize 2-time expansion to obtain a first pre-processing image, wherein the first pre-processing image comprises a turned mine car material image and a non-turned mine car material image;
s13, respectively rotating the first preprocessed image by using a random preset rotation angle to realize 6-time expansion to obtain a second preprocessed image, wherein the second preprocessed image comprises a left-turning first preprocessed image, a right-turning first preprocessed image and a non-rotating first preprocessed image;
step S14, respectively carrying out noise injection operation on the second preprocessed images to realize 24-time expansion to obtain preprocessed material images, wherein the preprocessed material images comprise the second preprocessed images injected with Gaussian noise, the second preprocessed images injected with multiplicative noise, the second preprocessed images injected with salt and pepper noise and the second preprocessed images injected without noise;
and S15, randomly dividing the 24 preprocessed material images expanded by each mine car material image into 6 groups of samples, wherein each group of samples comprises 4 preprocessed material images, and constructing a training sample library.
3. An intelligent recognition method according to claim 2, wherein the monitoring device is a camera.
4. The intelligent identification method according to claim 1, wherein step S2 specifically comprises:
step S21, constructing a first feature extraction module, a second feature extraction module, a third feature extraction module and a fourth feature extraction module;
step S22, constructing a splicing module for splicing the characteristics output by the first characteristic extraction module, the second characteristic extraction module, the third characteristic extraction module and the fourth characteristic extraction module;
s23, sequentially constructing a full connection layer, a Dropout layer and a Softmax layer, and classifying the features output by the splicing module to generate a classification result;
and S24, training the convolutional neural network model by using each group of samples in the training sample library.
5. The intelligent recognition method according to claim 4, wherein the first feature extraction module, the second feature extraction module, the third feature extraction module, and the fourth feature extraction module have the same structure.
6. The intelligent recognition method of claim 5, wherein each feature extraction module comprises a first convolution layer, a first normalization layer, a second convolution layer, a second normalization layer, a third convolution layer, a first maximum pooling layer, a first average pooling layer;
inputting the preprocessed material image into a first convolution layer, wherein the convolution kernel size is 7 multiplied by 7, and the input end of the first normalization layer is connected with the output end of the first convolution layer; the input end of the second convolution layer is connected with the output end of the first normalization layer, the convolution kernel size of the second convolution layer is 5 multiplied by 5, the input end of the second normalization layer is connected with the output end of the second convolution layer, the input end of the third convolution layer is connected with the output end of the second normalization layer, the convolution kernel size of the third convolution layer is 3 multiplied by 3, the input end of the first maximum pooling layer is connected with the output end of the third convolution layer, and the input end of the first average pooling layer is connected with the output end of the first maximum pooling layer.
7. An intelligent recognition method according to claim 6, wherein the classification results are coal, gangue and debris.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211133562.4A CN115205637B (en) | 2022-09-19 | 2022-09-19 | Intelligent identification method for mine car materials |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211133562.4A CN115205637B (en) | 2022-09-19 | 2022-09-19 | Intelligent identification method for mine car materials |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115205637A true CN115205637A (en) | 2022-10-18 |
| CN115205637B CN115205637B (en) | 2022-12-02 |
Family
ID=83573193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211133562.4A Active CN115205637B (en) | 2022-09-19 | 2022-09-19 | Intelligent identification method for mine car materials |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115205637B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295506A (en) * | 2016-07-25 | 2017-01-04 | 华南理工大学 | A kind of age recognition methods based on integrated convolutional neural networks |
| CN107886165A (en) * | 2017-12-30 | 2018-04-06 | 北京工业大学 | A kind of parallel-convolution neural net method based on CRT technology |
| CN109635784A (en) * | 2019-01-10 | 2019-04-16 | 重庆邮电大学 | Traffic sign recognition method based on improved convolutional neural networks |
| CN110135468A (en) * | 2019-04-24 | 2019-08-16 | 中国矿业大学(北京) | A kind of recognition methods of gangue |
| CN111860689A (en) * | 2020-07-31 | 2020-10-30 | 中国矿业大学 | Coal and gangue identification method based on phase consistency and light-weight convolutional neural network |
| CN112464873A (en) * | 2020-12-09 | 2021-03-09 | 携程计算机技术（上海）有限公司 | Model training method, face living body recognition method, system, device and medium |
| WO2021057426A1 (en) * | 2019-09-29 | 2021-04-01 | 腾讯科技（深圳）有限公司 | Method and apparatus for training image fusion processing model, device, and storage medium |
| CN112861881A (en) * | 2021-03-08 | 2021-05-28 | 太原理工大学 | Honeycomb lung recognition method based on improved MobileNet model |
| CN113052057A (en) * | 2021-03-19 | 2021-06-29 | 北京工业大学 | Traffic sign identification method based on improved convolutional neural network |
| CN113592825A (en) * | 2021-08-02 | 2021-11-02 | 安徽理工大学 | YOLO algorithm-based real-time coal gangue detection method |
| CN114049935A (en) * | 2021-11-23 | 2022-02-15 | 齐鲁工业大学 | HER2 image classification system based on multi-convolution neural network |
| CN114359727A (en) * | 2021-12-31 | 2022-04-15 | 华南农业大学 | Tea disease identification method and system based on lightweight optimization Yolo v4 |
| WO2022083383A1 (en) * | 2020-10-19 | 2022-04-28 | 北京字节跳动网络技术有限公司 | Image processing method and apparatus, electronic device and computer-readable storage medium |
| CN114612968A (en) * | 2022-03-02 | 2022-06-10 | 盐城工学院 | Convolutional neural network-based lip print identification method |
| CN114627109A (en) * | 2022-04-26 | 2022-06-14 | 河北工程大学 | Coal and gangue classification and identification method and process based on image enhancement and deep learning |
| US20220234077A1 (en) * | 2021-01-23 | 2022-07-28 | Anhui University of Science and Technology | Photoelectric Coal and Gangue Sorting Device and Sorting Method Therefor |
| US20220243910A1 (en) * | 2021-02-03 | 2022-08-04 | Xinqian Shu | System and method for calcining coal gangue |
-
2022
- 2022-09-19 CN CN202211133562.4A patent/CN115205637B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295506A (en) * | 2016-07-25 | 2017-01-04 | 华南理工大学 | A kind of age recognition methods based on integrated convolutional neural networks |
| CN107886165A (en) * | 2017-12-30 | 2018-04-06 | 北京工业大学 | A kind of parallel-convolution neural net method based on CRT technology |
| CN109635784A (en) * | 2019-01-10 | 2019-04-16 | 重庆邮电大学 | Traffic sign recognition method based on improved convolutional neural networks |
| CN110135468A (en) * | 2019-04-24 | 2019-08-16 | 中国矿业大学(北京) | A kind of recognition methods of gangue |
| WO2021057426A1 (en) * | 2019-09-29 | 2021-04-01 | 腾讯科技（深圳）有限公司 | Method and apparatus for training image fusion processing model, device, and storage medium |
| CN111860689A (en) * | 2020-07-31 | 2020-10-30 | 中国矿业大学 | Coal and gangue identification method based on phase consistency and light-weight convolutional neural network |
| WO2022083383A1 (en) * | 2020-10-19 | 2022-04-28 | 北京字节跳动网络技术有限公司 | Image processing method and apparatus, electronic device and computer-readable storage medium |
| CN112464873A (en) * | 2020-12-09 | 2021-03-09 | 携程计算机技术（上海）有限公司 | Model training method, face living body recognition method, system, device and medium |
| US20220234077A1 (en) * | 2021-01-23 | 2022-07-28 | Anhui University of Science and Technology | Photoelectric Coal and Gangue Sorting Device and Sorting Method Therefor |
| US20220243910A1 (en) * | 2021-02-03 | 2022-08-04 | Xinqian Shu | System and method for calcining coal gangue |
| CN112861881A (en) * | 2021-03-08 | 2021-05-28 | 太原理工大学 | Honeycomb lung recognition method based on improved MobileNet model |
| CN113052057A (en) * | 2021-03-19 | 2021-06-29 | 北京工业大学 | Traffic sign identification method based on improved convolutional neural network |
| CN113592825A (en) * | 2021-08-02 | 2021-11-02 | 安徽理工大学 | YOLO algorithm-based real-time coal gangue detection method |
| CN114049935A (en) * | 2021-11-23 | 2022-02-15 | 齐鲁工业大学 | HER2 image classification system based on multi-convolution neural network |
| CN114359727A (en) * | 2021-12-31 | 2022-04-15 | 华南农业大学 | Tea disease identification method and system based on lightweight optimization Yolo v4 |
| CN114612968A (en) * | 2022-03-02 | 2022-06-10 | 盐城工学院 | Convolutional neural network-based lip print identification method |
| CN114627109A (en) * | 2022-04-26 | 2022-06-14 | 河北工程大学 | Coal and gangue classification and identification method and process based on image enhancement and deep learning |
Non-Patent Citations (6)
| Title |
|---|
| LINGLING SU ET AL: "Research on Coal Gangue Identification by Using Convolutional Neural Network", 《2018 2ND IEEE ADVANCED INFORMATION MANAGEMENT,COMMUNICATES,ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IMCEC)》 * |
| SHIWEI LEI ET AL: "Visual classification method based on CNN for coal-gangue sorting robots", 《2020 5TH INTERNATIONAL CONFERENCE ON AUTOMATION, CONTROL AND ROBOTICS ENGINEERING (CACRE)》 * |
| 倪云峰 等: "基于卷积神经网络的煤矸石识别算法研究", 《现代电子技术》 * |
| 王雨晨: "基于残差网络的图像分类方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 雷世威 等: "基于改进 YOLOv3 的煤矸识别方法研究", 《矿业安全与环保》 * |
| 黄曼曼: "基于卷积神经网络的煤矸石图像识别方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115205637B (en) | 2022-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109639481B (en) | Deep learning-based network traffic classification method and system and electronic equipment | |
| Xu et al. | A hybrid deep-learning model for fault diagnosis of rolling bearings | |
| US20210370993A1 (en) | Computer vision based real-time pixel-level railroad track components detection system | |
| Khaing et al. | Development of control system for fruit classification based on convolutional neural network | |
| CN109815956B (en) | License plate character recognition method based on self-adaptive position segmentation | |
| CN103984959A (en) | Data-driven and task-driven image classification method | |
| CN106168539A (en) | Fault Diagnosis of Roller Bearings based on convolutional neural networks and system | |
| CN106462940A (en) | Generic object detection in images | |
| CN112396109A (en) | Motor bearing fault diagnosis method based on recursion graph and multilayer convolution neural network | |
| Gill et al. | An integrated approach using CNN-RNN-LSTM for classification of fruit images | |
| CN111738054B (en) | Behavior anomaly detection method based on space-time self-encoder network and space-time CNN | |
| CN112750129B (en) | Image semantic segmentation model based on feature enhancement position attention mechanism | |
| CN114898466A (en) | Video motion recognition method and system for smart factory | |
| Zhang et al. | An integrated approach for vehicle detection and type recognition | |
| Fu et al. | An improved deep convolutional neural network with multiscale convolution kernels for fault diagnosis of rolling bearing | |
| CN115205637B (en) | Intelligent identification method for mine car materials | |
| Zhang et al. | Weighted data normalization based on eigenvalues for artificial neural network classification | |
| CN111461184A (en) | XGB multi-dimensional operation and maintenance data anomaly detection method based on multivariate feature matrix | |
| CN116560341A (en) | Industrial robot fault diagnosis model and fault diagnosis method | |
| Năstăsescu et al. | Conditional wasserstein gan for energy load forecasting in large buildings | |
| CN115452376A (en) | Bearing fault diagnosis method based on improved lightweight deep convolution neural network | |
| CN114813963A (en) | Train wheel axle fault acoustic emission detection method based on TCN network | |
| CN114492644A (en) | Motor fault detection method based on improved neural network | |
| CN110991366A (en) | Shipping monitoring event identification method and system based on three-dimensional residual error network | |
| CN111563455A (en) | Damage identification method based on time series signal and compressed convolution neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |